Exploiting layerwise convexity of rectifier networks with sign constrained weights

By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majorization–minimization (MM) algorithms. We prove that the proposed two-hidden-layer SCRNs, which exhibit negative weights in...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks Jg. 105; S. 419 - 430
Hauptverfasser:	An, Senjian, Boussaid, Farid, Bennamoun, Mohammed, Sohel, Ferdous
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Elsevier Ltd 01.09.2018
Schlagworte:	Geometrically interpretable neural network Rectifier neural network The majorization–minimization algorithm Geometrically interpretable neural network The majorization–minimization algorithm Rectifier neural network
ISSN:	0893-6080, 1879-2782, 1879-2782
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!